{"url":"/dataset/wn18","name":"WN18","full_name":"WordNet18","description_markdown":"The **WN18** dataset has 18 relations scraped from WordNet for roughly 41,000 synsets, resulting in 141,442 triplets. It was found out that a large number of the test triplets can be found in the training set with another relation or the inverse relation. Therefore, a new version of the dataset WN18RR has been proposed to address this issue.\r\n\r\nSource: [http://nlpprogress.com/english/relation_prediction.html](http://nlpprogress.com/english/relation_prediction.html)","description_withheld":null,"homepage":"https://everest.hds.utc.fr/doku.php?id=en:transe","introduced_date":"2013-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/translating-embeddings-for-modeling-multi","title":"Translating Embeddings for Modeling Multi-relational Data","first_author":"Antoine Bordes","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Graphs","url":"/datasets/modality/graphs"}],"tasks":[{"name":"Link Prediction","url":"/task/link-prediction","datasets_with_task":"/datasets/task/link-prediction"},{"name":"Knowledge Graph Completion","url":"/task/knowledge-graph-completion","datasets_with_task":"/datasets/task/knowledge-graph-completion"},{"name":"Dynamic Link Prediction","url":"/task/dynamic-link-prediction","datasets_with_task":"/datasets/task/dynamic-link-prediction"},{"name":"Ancestor-descendant prediction","url":"/task/ancestor-descendant-prediction","datasets_with_task":"/datasets/task/ancestor-descendant-prediction"}],"languages":[],"variants":["WN18","WN18RR","WN18 (filtered)"],"data_loaders":[{"repo":"https://github.com/rusty1s/pytorch_geometric","url":"https://pytorch-geometric.readthedocs.io/en/latest/modules/datasets.html","frameworks":["pytorch"]},{"repo":"https://github.com/dmlc/dgl","url":"https://docs.dgl.ai/api/python/dgl.data.html#dgl.data.WN18Dataset","frameworks":["pytorch","tf","mxnet"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/wordnet","frameworks":["tf","jax"]},{"repo":"https://github.com/pykeen/pykeen","url":"https://pykeen.readthedocs.io/en/stable/api/pykeen.datasets.WN18.html","frameworks":["pytorch"]},{"repo":"https://github.com/bi-graph/emgraph","url":"https://github.com/bi-graph/emgraph","frameworks":["tf"]}],"num_papers_in_archive":485,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/link-prediction-on-wn18","task":"Link Prediction","dataset_variant":"WN18","rows":37,"metrics":["Hits@10","Hits@3","Hits@1","MRR","MR","training time (s)"],"first_row_in_archive_order":{"model":"Inverse Model","paper":"/paper/convolutional-2d-knowledge-graph-embeddings","metrics":{"Hits@1":"0.953","Hits@10":"0.964","Hits@3":"0.964","MR":"740","MRR":"0.963"},"code_links":[{"title":"TimDettmers/ConvE","url":"https://github.com/TimDettmers/ConvE"},{"title":"INK-USC/RE-Net","url":"https://github.com/INK-USC/RE-Net"},{"title":"thu-keg/eakit","url":"https://github.com/thu-keg/eakit"},{"title":"facebookresearch/ssl-relation-prediction","url":"https://github.com/facebookresearch/ssl-relation-prediction"},{"title":"bi-graph/emgraph","url":"https://github.com/bi-graph/emgraph"},{"title":"uma-pi1/kge-iclr20","url":"https://github.com/uma-pi1/kge-iclr20"},{"title":"LB0828/conve_reproduce","url":"https://github.com/LB0828/conve_reproduce"},{"title":"oliver-lloyd/kge_param_sens","url":"https://github.com/oliver-lloyd/kge_param_sens"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/dynamic-link-prediction-on-wn18-filtered","task":"Dynamic Link Prediction","dataset_variant":"WN18 (filtered)","rows":1,"metrics":["Mrr@2"],"first_row_in_archive_order":{"model":"ComplEx-N3 (reciprocal)","paper":"/paper/canonical-tensor-decomposition-for-knowledge","metrics":{"Mrr@2":"0.9"},"code_links":[{"title":"facebookresearch/kbc","url":"https://github.com/facebookresearch/kbc"},{"title":"facebookresearch/ssl-relation-prediction","url":"https://github.com/facebookresearch/ssl-relation-prediction"},{"title":"twktheainur/kbc","url":"https://github.com/twktheainur/kbc"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/link-prediction-on-wn18-filtered","task":"Link Prediction","dataset_variant":"WN18 (filtered)","rows":1,"metrics":["Hits@10","MR"],"first_row_in_archive_order":{"model":"ParTransH","paper":"/paper/efficient-parallel-translating-embedding-for","metrics":{"Hits@10":"76.6","MR":"203"},"code_links":[{"title":"zdh2292390/ParTrans-X","url":"https://github.com/zdh2292390/ParTrans-X"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/quatde-dynamic-quaternion-embedding-for","title":"QuatDE: Dynamic Quaternion Embedding for Knowledge Graph Completion","date":"2021-05-19","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/dense-an-enhanced-non-abelian-group","title":"DensE: An Enhanced Non-commutative Representation for Knowledge Graph Embedding with Adaptive Semantic Hierarchy","date":"2020-08-11","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/pykeen-1-0-a-python-library-for-training-and","title":"PyKEEN 1.0: A Python Library for Training and Evaluating Knowledge Graph Embeddings","date":"2020-07-28","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":0,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/multi-partition-embedding-interaction-with","title":"Multi-Partition Embedding Interaction with Block Term Format for Knowledge Graph Completion","date":"2020-06-29","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/knowledge-graph-embedding-with-linear","title":"LineaRE: Simple but Powerful Knowledge Graph Embedding for Link Prediction","date":"2020-04-21","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/representation-learning-with-ordered-relation","title":"Representation Learning with Ordered Relation Paths for Knowledge Graph Completion","date":"2019-09-26","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/logicenn-a-neural-based-knowledge-graphs","title":"LogicENN: A Neural Based Knowledge Graphs Embedding Model with Logical Rules","date":"2019-08-20","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/augmenting-and-tuning-knowledge-graph","title":"Augmenting and Tuning Knowledge Graph Embeddings","date":"2019-07-01","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/adaptive-convolution-for-multi-relational","title":"Adaptive Convolution for Multi-Relational Learning","date":"2019-06-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/mde-multi-distance-embeddings-for-link","title":"MDE: Multiple Distance Embeddings for Link Prediction in Knowledge Graphs","date":"2019-05-25","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/autokge-searching-scoring-functions-for","title":"AutoSF: Searching Scoring Functions for Knowledge Graph Embedding","date":"2019-04-26","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/quaternion-knowledge-graph-embedding","title":"Quaternion Knowledge Graph Embeddings","date":"2019-04-23","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/analyzing-knowledge-graph-embedding-methods","title":"Analyzing Knowledge Graph Embedding Methods from a Multi-Embedding Interaction Perspective","date":"2019-03-27","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/graphvite-a-high-performance-cpu-gpu-hybrid","title":"GraphVite: A High-Performance CPU-GPU Hybrid System for Node Embedding","date":"2019-03-02","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":0,"samples_unverified":7,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/rotate-knowledge-graph-embedding-by","title":"RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space","date":"2019-02-26","rows_on_this_dataset":2,"code_links":10,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":0,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/tucker-tensor-factorization-for-knowledge","title":"TuckER: Tensor Factorization for Knowledge Graph Completion","date":"2019-01-28","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/nscaching-simple-and-efficient-negative","title":"NSCaching: Simple and Efficient Negative Sampling for Knowledge Graph Embedding","date":"2018-12-16","rows_on_this_dataset":1,"code_links":6,"syntology":null},{"paper":"/paper/augmenting-compositional-models-for-knowledge","title":"Augmenting Compositional Models for Knowledge Base Completion Using Gradient Representations","date":"2018-11-02","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/auggan-cross-domain-adaptation-with-gan-based","title":"AugGAN: Cross Domain Adaptation with GAN-based Data Augmentation","date":"2018-09-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/hypernetwork-knowledge-graph-embeddings","title":"Hypernetwork Knowledge Graph Embeddings","date":"2018-08-21","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/canonical-tensor-decomposition-for-knowledge","title":"Canonical Tensor Decomposition for Knowledge Base Completion","date":"2018-06-19","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/simple-embedding-for-link-prediction-in","title":"SimplE Embedding for Link Prediction in Knowledge Graphs","date":"2018-02-13","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/kbgan-adversarial-learning-for-knowledge","title":"KBGAN: Adversarial Learning for Knowledge Graph Embeddings","date":"2017-11-11","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":0,"samples_unverified":7,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/convolutional-2d-knowledge-graph-embeddings","title":"Convolutional 2D Knowledge Graph Embeddings","date":"2017-07-05","rows_on_this_dataset":2,"code_links":8,"syntology":null},{"paper":"/paper/analogical-inference-for-multi-relational","title":"Analogical Inference for Multi-Relational Embeddings","date":"2017-05-06","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/efficient-parallel-translating-embedding-for","title":"Efficient Parallel Translating Embedding For Knowledge Graphs","date":"2017-03-30","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/discriminative-gaifman-models","title":"Discriminative Gaifman Models","date":"2016-10-28","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/complex-embeddings-for-simple-link-prediction","title":"Complex Embeddings for Simple Link Prediction","date":"2016-06-20","rows_on_this_dataset":1,"code_links":9,"syntology":null},{"paper":"/paper/holographic-embeddings-of-knowledge-graphs","title":"Holographic Embeddings of Knowledge Graphs","date":"2015-10-16","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":0,"samples_unverified":8,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/knowledge-graph-embedding-via-dynamic-mapping","title":"Knowledge Graph Embedding via Dynamic Mapping Matrix","date":"2015-07-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/embedding-entities-and-relations-for-learning","title":"Embedding Entities and Relations for Learning and Inference in Knowledge Bases","date":"2014-12-20","rows_on_this_dataset":1,"code_links":10,"syntology":null},{"paper":"/paper/translating-embeddings-for-modeling-multi","title":"Translating Embeddings for Modeling Multi-relational Data","date":"2013-12-01","rows_on_this_dataset":1,"code_links":8,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":7,"samples_harvested":37,"samples_ran":2,"samples_unverified":35,"pointer_only_for_licence":2,"papers_with_no_sample_that_ran":6,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}